English
Related papers

Related papers: Positional Encoding Helps Recurrent Neural Network…

200 papers

Accurate predictions rely on the expressiveness power of graph deep learning frameworks like graph neural networks and graph transformers, where a positional encoding mechanism has become much more indispensable in recent state-of-the-art…

Machine Learning · Computer Science 2025-06-12 Katherine Tieu , Dongqi Fu , Zihao Li , Ross Maciejewski , Jingrui He

Hyperdimensional Computing affords simple, yet powerful operations to create long Hyperdimensional Vectors (hypervectors) that can efficiently encode information, be used for learning, and are dynamic enough to be modified on the fly. In…

Symbolic Computation · Computer Science 2022-06-01 Peter Sutor , Dehao Yuan , Douglas Summers-Stay , Cornelia Fermuller , Yiannis Aloimonos

The groundbreaking performance of deep neural networks (NNs) promoted a surge of interest in providing a mathematical basis to deep learning theory. Low-rank tensor decompositions are specially befitting for this task due to their close…

Machine Learning · Computer Science 2025-12-18 Ricardo Borsoi , Konstantin Usevich , Marianne Clausel

Leveraging the extraordinary phenomena of quantum superposition and quantum correlation, quantum computing offers unprecedented potential for addressing challenges beyond the reach of classical computers. This paper tackles two pivotal…

Quantum Physics · Physics 2023-12-14 Ming-Hao Wang , Hua Lu

Recent advances of video captioning often employ a recurrent neural network (RNN) as the decoder. However, RNN is prone to diluting long-term information. Recent works have demonstrated memory network (MemNet) has the advantage of storing…

Computer Vision and Pattern Recognition · Computer Science 2020-02-28 Aming Wu , Yahong Han

Positional encoding has become a standard component in graph learning, especially for graph Transformers and other models that must distinguish structurally similar nodes, yet its fundamental identifiability remains poorly understood. In…

Information Theory · Computer Science 2026-03-27 Zimo Yan , Zheng Xie , Chang Liu , Yiqin Lv , Runfan Duan

Inspired by "predictive coding" - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural…

Computer Vision and Pattern Recognition · Computer Science 2018-10-29 Kuan Han , Haiguang Wen , Yizhen Zhang , Di Fu , Eugenio Culurciello , Zhongming Liu

We propose tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order ones. The problem of parameter learning is challenging, as it corresponds…

Machine Learning · Statistics 2018-12-11 Jiahao Su , Jingling Li , Bobby Bhattacharjee , Furong Huang

We propose an off-line approach to explicitly encode temporal patterns spatially as different types of images, namely, Gramian Angular Fields and Markov Transition Fields. This enables the use of techniques from computer vision for feature…

Machine Learning · Computer Science 2015-09-25 Zhiguang Wang , Tim Oates

Deep neural networks (DNNs) are widely used in pattern-recognition tasks for which a human comprehensible, quantitative description of the data-generating process, e.g., in the form of equations, cannot be achieved. While doing so, DNNs…

Machine Learning · Computer Science 2022-10-12 Antoine Garcon , Julian Vexler , Dmitry Budker , Stefan Kramer

Over the long history of machine learning, which dates back several decades, recurrent neural networks (RNNs) have been used mainly for sequential data and time series and generally with 1D information. Even in some rare studies on 2D…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Nguyen Huu Phong , Bernardete Ribeiro

Positional Encodings (PEs) are used to inject word-order information into transformer-based language models. While they can significantly enhance the quality of sentence representations, their specific contribution to language models is not…

Computation and Language · Computer Science 2023-10-20 Lihu Chen , Gaël Varoquaux , Fabian M. Suchanek

The attention mechanism is a critical component of Large Language Models (LLMs) that allows tokens in a sequence to interact with each other, but is order-invariant. Incorporating position encoding (PE) makes it possible to address by…

Computation and Language · Computer Science 2024-05-31 Olga Golovneva , Tianlu Wang , Jason Weston , Sainbayar Sukhbaatar

Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness of position-based addressing. Many current methods enforce…

Computation and Language · Computer Science 2025-08-22 Jiajun Zhu , Peihao Wang , Ruisi Cai , Jason D. Lee , Pan Li , Zhangyang Wang

Graph Neural Networks are notorious for its memory consumption. A recent Transformer-based GNN called Graph Transformer is shown to obtain superior performances when long range dependencies exist. However, combining graph data and…

Machine Learning · Computer Science 2024-03-25 Eugene Ku

Neural encoding plays an important role in faithfully describing the temporally rich patterns, whose instances include human speech and environmental sounds. For tasks that involve classifying such spatio-temporal patterns with the Spiking…

Neural and Evolutionary Computing · Computer Science 2019-09-27 Zihan Pan , Jibin Wu , Yansong Chua , Malu Zhang , Haizhou Li

Expressive text encoders such as RNNs and Transformer Networks have been at the center of NLP models in recent work. Most of the effort has focused on sentence-level tasks, capturing the dependencies between words in a single sentence, or…

Computation and Language · Computer Science 2021-09-15 Manuel Widmoser , Maria Leonor Pacheco , Jean Honorio , Dan Goldwasser

Positional Encodings (PEs) are essential for injecting structural information into Graph Neural Networks (GNNs), particularly Graph Transformers, yet their empirical impact remains insufficiently understood. We introduce a unified…

Machine Learning · Computer Science 2026-01-15 Florian Grötschla , Jiaqing Xie , Roger Wattenhofer

We revisit hierarchical bracketing encodings from a practical perspective in the context of dependency graph parsing. The approach encodes graphs as sequences, enabling linear-time parsing with $n$ tagging actions, and still representing…

Computation and Language · Computer Science 2025-09-12 Ana Ezquerro , Carlos Gómez-Rodríguez , David Vilares

In transformers, the positional encoding (PE) provides essential information that distinguishes the position and order amongst tokens in a sequence. Most prior investigations of PE effects on generalization were tailored to 1D input…

Machine Learning · Computer Science 2025-06-24 Takuya Ito , Luca Cocchi , Tim Klinger , Parikshit Ram , Murray Campbell , Luke Hearne